{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K2W32HTSXZSK6T2NFDQUSWU76X","short_pith_number":"pith:K2W32HTS","schema_version":"1.0","canonical_sha256":"56adbd1e72be64af4f4d28e1495a9ff5f4f26d9e1c17c06c55213fd02e5079a7","source":{"kind":"arxiv","id":"2506.12087","version":1},"attestation_state":"computed","paper":{"title":"Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Chunyan Miao, Hailong Shi, Peilin Zhao, Pengcheng Wu, Wanjin Feng, Wenqian Du, Xingyu Gao","submitted_at":"2025-06-10T13:27:27Z","abstract_excerpt":"Spiking Neural Networks (SNNs) often suffer from high time complexity $O(T)$ due to the sequential processing of $T$ spikes, making training computationally expensive.\n  In this paper, we propose a novel Fixed-point Parallel Training (FPT) method to accelerate SNN training without modifying the network architecture or introducing additional assumptions.\n  FPT reduces the time complexity to $O(K)$, where $K$ is a small constant (usually $K=3$), by using a fixed-point iteration form of Leaky Integrate-and-Fire (LIF) neurons for all $T$ timesteps.\n  We provide a theoretical convergence analysis o"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.12087","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2025-06-10T13:27:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eaaf3a43c8f569a1fb9a1cb4c55b8cc08b1bfa479dad688712181192489fa72b","abstract_canon_sha256":"a7e660e9cc5b9c550e8094772c31836fea850cd9d85d1bec497a30251530e42e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:16.862280Z","signature_b64":"HrDnX6qaC0NSf+W8XLrLCWe2b5CpsY2jNVghfgEgX7KqHvOqXCxGSdNeYtHyWvEl8RaU/8WJn+9VfLbOWinhDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56adbd1e72be64af4f4d28e1495a9ff5f4f26d9e1c17c06c55213fd02e5079a7","last_reissued_at":"2026-07-05T11:21:16.861870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:16.861870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Chunyan Miao, Hailong Shi, Peilin Zhao, Pengcheng Wu, Wanjin Feng, Wenqian Du, Xingyu Gao","submitted_at":"2025-06-10T13:27:27Z","abstract_excerpt":"Spiking Neural Networks (SNNs) often suffer from high time complexity $O(T)$ due to the sequential processing of $T$ spikes, making training computationally expensive.\n  In this paper, we propose a novel Fixed-point Parallel Training (FPT) method to accelerate SNN training without modifying the network architecture or introducing additional assumptions.\n  FPT reduces the time complexity to $O(K)$, where $K$ is a small constant (usually $K=3$), by using a fixed-point iteration form of Leaky Integrate-and-Fire (LIF) neurons for all $T$ timesteps.\n  We provide a theoretical convergence analysis o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12087","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.12087/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.12087","created_at":"2026-07-05T11:21:16.861931+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12087v1","created_at":"2026-07-05T11:21:16.861931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12087","created_at":"2026-07-05T11:21:16.861931+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2W32HTSXZSK","created_at":"2026-07-05T11:21:16.861931+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2W32HTSXZSK6T2N","created_at":"2026-07-05T11:21:16.861931+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2W32HTS","created_at":"2026-07-05T11:21:16.861931+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K2W32HTSXZSK6T2NFDQUSWU76X","json":"https://pith.science/pith/K2W32HTSXZSK6T2NFDQUSWU76X.json","graph_json":"https://pith.science/api/pith-number/K2W32HTSXZSK6T2NFDQUSWU76X/graph.json","events_json":"https://pith.science/api/pith-number/K2W32HTSXZSK6T2NFDQUSWU76X/events.json","paper":"https://pith.science/paper/K2W32HTS"},"agent_actions":{"view_html":"https://pith.science/pith/K2W32HTSXZSK6T2NFDQUSWU76X","download_json":"https://pith.science/pith/K2W32HTSXZSK6T2NFDQUSWU76X.json","view_paper":"https://pith.science/paper/K2W32HTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12087&json=true","fetch_graph":"https://pith.science/api/pith-number/K2W32HTSXZSK6T2NFDQUSWU76X/graph.json","fetch_events":"https://pith.science/api/pith-number/K2W32HTSXZSK6T2NFDQUSWU76X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2W32HTSXZSK6T2NFDQUSWU76X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2W32HTSXZSK6T2NFDQUSWU76X/action/storage_attestation","attest_author":"https://pith.science/pith/K2W32HTSXZSK6T2NFDQUSWU76X/action/author_attestation","sign_citation":"https://pith.science/pith/K2W32HTSXZSK6T2NFDQUSWU76X/action/citation_signature","submit_replication":"https://pith.science/pith/K2W32HTSXZSK6T2NFDQUSWU76X/action/replication_record"}},"created_at":"2026-07-05T11:21:16.861931+00:00","updated_at":"2026-07-05T11:21:16.861931+00:00"}